Re: [PATCH 1/2] drm/amdgpu: handle the return for sync wait

[Christian König <ckoenig.leichtzumerken@xxxxxxxxx>]

Am 20.10.23 um 11:59 schrieb Emily Deng:
> Add error handling for amdgpu_sync_wait.
>
> Signed-off-by: Emily Deng <Emily.Deng@xxxxxxx>

Reviewed-by: Christian König <christian.koenig@xxxxxxx> for this one.

Going to discuss with Felix later today what we do with the timeout.

Christian.

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 9 ++++++---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c          | 6 +++++-
>   2 files changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index 54f31a420229..3011c191d7dd 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -2668,7 +2668,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
>   
>   unreserve_out:
>   	ttm_eu_backoff_reservation(&ticket, &resv_list);
> -	amdgpu_sync_wait(&sync, false);
> +	ret = amdgpu_sync_wait(&sync, false);
>   	amdgpu_sync_free(&sync);
>   out_free:
>   	kfree(pd_bo_list_entries);
> @@ -2939,8 +2939,11 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
>   	}
>   
>   	/* Wait for validate and PT updates to finish */
> -	amdgpu_sync_wait(&sync_obj, false);
> -
> +	ret = amdgpu_sync_wait(&sync_obj, false);
> +	if (ret) {
> +		pr_err("Failed to wait for validate and PT updates to finish\n");
> +		goto validate_map_fail;
> +	}
>   	/* Release old eviction fence and create new one, because fence only
>   	 * goes from unsignaled to signaled, fence cannot be reused.
>   	 * Use context and mm from the old fence.
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> index 70fe3b39c004..a63139277583 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
> @@ -1153,7 +1153,11 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
>   	}
>   	amdgpu_sync_fence(&sync, vm->last_update);
>   
> -	amdgpu_sync_wait(&sync, false);
> +	r = amdgpu_sync_wait(&sync, false);
> +	if (r) {
> +		DRM_ERROR("failed to wait sync\n");
> +		goto error;
> +	}
>   	ttm_eu_backoff_reservation(&ticket, &list);
>   
>   	amdgpu_sync_free(&sync);